Agent Lightning

Microsoft's framework for training AI agents with reinforcement learning, automatic prompt optimization, and supervised fine-tuning.

Quick Start

Installation

pip install agentlightning

For nightly builds:

pip install --upgrade --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ --pre agentlightning

Minimal Integration (Zero Code Change)

Add agl.emit_xxx() helpers to your existing agent:

import agentlightning as agl

# Your existing agent code
def my_agent(task):
    agl.emit_input(task)  # Track input
    
    response = llm.generate(task)
    agl.emit_output(response)  # Track output
    
    reward = evaluate(response)
    agl.emit_reward(reward)  # Track reward
    
    return response

Core Concepts

Architecture Flow

Agent (your code) → agl.emit_xxx() → Spans → LightningStore → Algorithm → Updated Resources

Key Components

Component	Purpose
LightningStore	Central hub for traces, tasks, and resources
Tracer	Collects spans from agent execution
Algorithm	Consumes traces, produces improvements
Trainer	Orchestrates training loop

Instrumentation

Emit Functions

import agentlightning as agl

# Basic emissions
agl.emit_input(prompt)           # Track input to agent
agl.emit_output(response)        # Track agent output
agl.emit_reward(score)           # Track reward signal
agl.emit_tool_call(name, args)   # Track tool usage
agl.emit_tool_result(result)     # Track tool results

Tracer Context

from agentlightning import Tracer

tracer = Tracer(store=store)

with tracer.trace_context(task_id="task-123"):
    # All emissions within this context are grouped
    result = agent.run(task)
    
# Retrieve trace after execution
trace = tracer.get_last_trace()

OpenTelemetry Integration

Agent Lightning integrates with OpenTelemetry: